Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    academic citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conce
    -0.09
     cons
    -0.08
     avanzada
    -0.08
     synd
    -0.08
    -0.08
     twilight
    -0.08
     avanzado
    -0.07
     cualquiera
    -0.07
     avanz
    -0.07
     Dolores
    -0.07
    POSITIVE LOGITS
     moral
    0.08
     જેવા
    0.08
    己
    0.07
    ავი
    0.07
    ანი
    0.07
     milion
    0.07
     brz
    0.07
    галтер
    0.07
     किन
    0.07
     جات
    0.07
    Act Density 0.010%
    No Known Activations